Cover Image

ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gao, Yiling, Wei, Hongchen, Chen, Zhenzhong
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Visual Context Window Extension: A New Perspective for Long Video Understanding
by: Wei, Hongchen, et al.
Published: (2024)

Training-Free Reasoning and Reflection in MLLMs
by: Wei, Hongchen, et al.
Published: (2025)

LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs Scaling
by: Zhang, Zhihan, et al.
Published: (2025)

ETC: training-free diffusion models acceleration with Error-aware Trend Consistency
by: Xie, Jiajian, et al.
Published: (2025)

Balancing Saliency and Coverage: Semantic Prominence-Aware Budgeting for Visual Token Compression in VLMs
by: Lee, Jaehoon, et al.
Published: (2026)

Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates
by: Ye, Yixuan, et al.
Published: (2024)

ApET: Approximation-Error Guided Token Compression for Efficient VLMs
by: Ma, Qiankun, et al.
Published: (2026)

LongCaptioning: Unlocking the Power of Long Video Caption Generation in Large Multimodal Models
by: Wei, Hongchen, et al.
Published: (2025)

Towards Lossless Ultimate Vision Token Compression for VLMs
by: Zheng, Dehua, et al.
Published: (2025)

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
by: Fang, Zhengyao, et al.
Published: (2026)

RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing Forgeries
by: Tan, Zhihong, et al.
Published: (2025)

TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
by: Tan, Xudong, et al.
Published: (2025)

Exploring Long- and Short-Range Temporal Information for Learned Video Compression
by: Wang, Huairui, et al.
Published: (2022)

DiffVC-RT: Towards Practical Real-Time Diffusion-based Perceptual Neural Video Compression
by: Ma, Wenzhuo, et al.
Published: (2026)

Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
by: Peng, Tianfan, et al.
Published: (2025)

Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification
by: Jin, Xin, et al.
Published: (2026)

Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
by: Ma, Yinchao, et al.
Published: (2026)

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
by: Li, Duo, et al.
Published: (2025)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

Compressing Multi-Task Model for Autonomous Driving via Pruning and Knowledge Distillation
by: Wang, Jiayuan, et al.
Published: (2025)

TokenSeg: Efficient 3D Medical Image Segmentation via Hierarchical Visual Token Compression
by: Zeng, Sen, et al.
Published: (2026)

Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMs
by: Zhang, Song, et al.
Published: (2026)

Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding
by: Liu, Xiangrui, et al.
Published: (2025)

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
by: Zhang, Zheyu, et al.
Published: (2026)

Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
by: Zhang, Qizhe, et al.
Published: (2024)

Leverage Task Context for Object Affordance Ranking
by: Huang, Haojie, et al.
Published: (2024)

Diffusion-based Perceptual Neural Video Compression with Temporal Diffusion Information Reuse
by: Ma, Wenzhuo, et al.
Published: (2025)

Scaling Mesh Generation via Compressive Tokenization
by: Weng, Haohan, et al.
Published: (2024)

From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs
by: Cao, Ang, et al.
Published: (2025)

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders
by: Cao, Jiajun, et al.
Published: (2025)

Extreme Model Compression for Edge Vision-Language Models: Sparse Temporal Token Fusion and Adaptive Neural Compression
by: Tanvir, Md Tasnin, et al.
Published: (2025)

Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth
by: Wu, Yuhuan, et al.
Published: (2026)

Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
by: Chen, Yanlong, et al.
Published: (2026)

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
by: Qin, Yiming, et al.
Published: (2025)

T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
by: Yeh, Chen, et al.
Published: (2024)

Beyond Shortcuts: Mitigating Visual Illusions in Frozen VLMs via Qualitative Reasoning
by: Guo, Hao, et al.
Published: (2026)

Visual-Geometric Collaborative Guidance for Affordance Learning
by: Luo, Hongchen, et al.
Published: (2024)

Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs
by: Zhang, Xintong, et al.
Published: (2025)

Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding
by: Chen, Tianyu, et al.
Published: (2025)

Task-Related Token Compression in Multimodal Large Language Models from an Explainability Perspective
by: Lei, Lei, et al.
Published: (2025)